© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 69708
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a connection or relationship between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mitt
    -0.07
    ocs
    -0.07
    verture
    -0.07
    ouri
    -0.07
    ÙģÙĩ
    -0.06
     æ¬
    -0.06
    ijo
    -0.06
    folios
    -0.06
    ckett
    -0.06
     créd
    -0.06
    POSITIVE LOGITS
    .any
    0.06
     any
    0.06
    emann
    0.06
    employees
    0.06
     household
    0.06
     busiest
    0.06
    ame
    0.06
     involved
    0.06
     employees
    0.06
    bsites
    0.06
    Activations Density 0.000%

    No Known Activations